ANOMALY DETECTION FOR AN ORAL HEALTH CARE APPLICATION USING ONE CLASS YOLOV3

Abstract

In this report, we apply an anomaly detection algorithm to a mobile oral health care application. In particular, we have investigated one class YOLOv3 as an anomaly detec- tion model to classify pictures of mouths which will be used as inputs in the following machine learning model. We have achieved outstanding performances by proposing appropriate anno- tation strategies for our data sets and modifying the loss function. Moreover, the model can classify not only oral and non-oral pictures but also output preprocessed pictures that only con- tain the area around the lips by using the predicted bounding box. Thus, the model performs prediction and preprocessing simultaneously.